Article
Environmental Sciences
Zhong Chen, Jun Zhao, He Deng
Summary: Semantic segmentation has been important in remote sensing image interpretation. The current encoder-decoder models have limitations in utilizing context dependencies and multi-scale features. To address these limitations, a global attention gate (GAG) module is proposed to fully utilize context and multi-scale features, resulting in better segmentation results.
Article
Geochemistry & Geophysics
Chen Xu, Xiaoping Du, Xiangtao Fan, Zhenzhen Yan, Xujie Kang, Junjie Zhu, Zhongyang Hu
Summary: This research analyzed the processing flow of remote sensing big data from the perspective of computer science and remote sensing science, proposing a modular framework. By introducing computation ready data as a dynamic data type to connect key modules of the framework, it significantly reduces experimental costs for remote sensing researchers.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Environmental Sciences
Lilu Zhu, Xiaolu Su, Xianqing Tai
Summary: The article presents a hierarchical multi-dimensional hybrid indexing model (HMDH) for processing unified organization and data sharing service capabilities of remote sensing data, which can effectively improve query efficiency.
Article
Geography, Physical
Wenbo Wang, Huijun Zhou, Senyuan Zheng, Guonian Lue, Liangchen Zhou
Summary: This paper aims to estimate global ocean surface current using a global isotropic hexagonal grid from satellite remote sensing data. The gridded satellite altimeter data and wind data are interpolated into the centre of the global isotropic hexagonal grid. Geostrophic and Ekman currents components are estimated according to the Lagerlof Ocean currents theory. The results show that the ocean surface currents estimated based on the global isotropic hexagonal grid have considerable accuracy, with improvement over rectangular lat/lon grids.
INTERNATIONAL JOURNAL OF DIGITAL EARTH
(2023)
Article
Computer Science, Artificial Intelligence
Qiong Chen, Mengxing Huang, Hao Wang, Guangquan Xu
Summary: Discretization is an important data preprocessing technique in data mining, especially in industrial control. However, traditional discretization methods have shortcomings, particularly in the preprocessing of high-resolution remote sensing big data, where necessary information is lost. This study proposes a discretization method for high-resolution remote sensing big data, which determines the membership degree of each pixel using linear decomposition and a fuzzy rough model, and selects discrete breakpoints using an adaptive genetic algorithm. The method achieves optimal discretization scheme in the shortest time by parallel computing the individual fitness of the population using a MapReduce framework.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2022)
Article
Engineering, Electrical & Electronic
Yang Liu, Lanxue Dang, Shenshen Li, Kun Cai, Xianyu Zuo
Summary: This article summarizes the data type and processing theory model of RS-STBD, high-performance algorithm design, and architecture design of complex remote sensing application systems. It also analyzes current research problems and prospects the future development trends of RS-STBD.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Environmental Sciences
Jie Chen, Libo Yang, Hao Wang, Jingru Zhu, Geng Sun, Xiaojun Dai, Min Deng, Yan Shi
Summary: The paper proposes a novel high-resolution road extraction network, CR-HR-RoadNet, which addresses the issues of incomplete and disjointed road extraction results by incorporating local and global context reasoning. The application of a multi-scale feature representation module and a lightweight coordinate attention module enables CR-HR-RoadNet to achieve superior extraction accuracy across various road datasets.
Article
Computer Science, Interdisciplinary Applications
Steven Rubinyi, Brian Blankespoor, Jim W. Hall
Summary: Several high-resolution global gridded population data sets are available, relying increasingly on a single ancillary data set to inform population distribution. Testing in New York City showed that model performance generally improves as binary masking variables become more limiting and density variables become more pronounced. Careful consideration is needed for application due to their potential to amplify both positive results and errors.
COMPUTERS ENVIRONMENT AND URBAN SYSTEMS
(2021)
Article
Computer Science, Information Systems
Xuejun Guo, Ruisen Zhou
Summary: This paper proposes a novel data augmentation method for extracting partially occluded roads from high spatial resolution remote sensing images. By simulating occlusion and replacing road pixels with non-road pixels, the method generates various levels of occlusion and improves the robustness and accuracy of existing algorithms.
Article
Computer Science, Artificial Intelligence
Xiaoyan Lu, Yanfei Zhong, Liangpei Zhang
Summary: This paper proposes an open-source data-driven domain-specific representation (OSM-DOER) framework for cross-domain road detection. By aligning the distribution of spatial structure information and learning domain-specific texture information, the framework overcomes the limited generalization ability of deep learning methods. Moreover, the use of open-source OpenStreetMap road centerline data enhances the representation of target domain data distribution. Extensive experiments demonstrate the superiority of the proposed framework in road detection and its potential for future applications.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2022)
Article
Computer Science, Hardware & Architecture
Sa Zhu, Weixuan Ma, Jian Yao
Summary: In this paper, a feature matching algorithm based on geometric constraints is proposed, which combines global and local geometric constraints to achieve high precision and efficiency in feature matching on high-resolution remote sensing images. The algorithm can obtain more robust and accurate results compared to other algorithms.
COMPUTERS & ELECTRICAL ENGINEERING
(2022)
Article
Computer Science, Hardware & Architecture
Xianghe Ma
Summary: Digital image processing plays a significant role in various fields, particularly in remote sensing image processing, involving the acquisition, enhancement, analysis, encoding, transmission, and storage of remote sensing images. However, the large volume of images produced by ultra-high resolution optical remote sensing satellites poses challenges for existing transmission, storage, and processing technologies. This paper proposes a spatio-temporal compression pipeline for remote sensing images, using lossy compression methods with ultra-high compression ratios to reduce overhead and maintain the image quality. Experimental results demonstrate that the proposed method outperforms classical image compression techniques like JPEG-2000.
Article
Geochemistry & Geophysics
Xiran Zhou, Jiawei Chen, Todd E. Rakstad, Mike Ploughe, Pingbo Tang
Summary: This study examines the potential of using high-resolution remote sensing data (such as Planet) to measure chlorophyll degree in canal waters, finding that while Planet can represent relative changes in chlorophyll concentration, new algorithms are needed for accurate results in a canal system.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2021)
Article
Environmental Sciences
Wanying Song, Xinwei Zhou, Shiru Zhang, Yan Wu, Peng Zhang
Summary: This paper introduces a novel Global and Local Feature Fusion Network (GLF-Net) for semantic segmentation of high-resolution remote sensing images. The network effectively excavates and fuses features in the images by incorporating extensive contextual information and fine-grained features. Experimental results demonstrate that GLF-Net greatly improves segmentation accuracy.
Article
Computer Science, Artificial Intelligence
Yansheng Li, Jiayi Ma, Yongjun Zhang
Summary: The paper discusses the importance of image retrieval in RS big data, as well as related applications and challenges, and provides publicly open datasets, evaluation metrics, and mainstream methods. The authors also point out future research directions for RS big data mining.
INFORMATION FUSION
(2021)
Article
Agronomy
Lenka Bartosova, Milan Fischer, Jan Balek, Monika Blahova, Lucie Kudlackova, Filip Chuchma, Petr Hlavinka, Martin Mozny, Pavel Zahradnicek, Nicole Wall, Michael Hayes, Christopher Hain, Martha Anderson, Wolfgang Wagner, Zdenek Zalud, Miroslav Trnka
Summary: The Czech Drought Monitor System (CzechDM) utilizes in situ observations by farmers to provide real-time data on drought conditions, which were compared and validated with modeling outputs and other monitoring tools. The study found that farmers' reports provide early insights into drought impacts on crop yield and enhance drought monitoring significantly.
AGRICULTURAL AND FOREST METEOROLOGY
(2022)
Article
Water Resources
Mariette Vreugdenhil, Borbala Szeles, Jose Luis Salinas, Peter Strauss, Markus Oismueller, Patrick Hogan, Wolfgang Wagner, Juraj Parajka, Guenter Bloschl
Summary: This study in an agricultural catchment in Austria investigates the non-linear relationship between event peak runoff and potential controls, finding that hillslopes dominated by ephemeral overland flow exhibit the most non-linear runoff generation behavior while runoff through tile drains and wetlands is more linear. The mix of different mechanisms in the catchment leads to a more linear response.
HYDROLOGICAL PROCESSES
(2022)
Article
Environmental Sciences
Wolfgang Wagner, Roland Lindorfer, Thomas Melzer, Sebastian Hahn, Bernhard Bauer-Marschallinger, Keith Morrison, Jean-Christophe Calvet, Stephen Hobbs, Raphael Quast, Isabella Greimeister-Pfeil, Mariette Vreugdenhil
Summary: This paper proposes an exponential model to describe the impact of subsurface scatterers on backscatter measurements and provides evidence for the widespread occurrence and importance of subsurface scattering phenomenon.
REMOTE SENSING OF ENVIRONMENT
(2022)
Article
Remote Sensing
Alena Dostalova, Claudio Navacchi, Isabella Greimeister-Pfeil, David Small, Wolfgang Wagner
Summary: This study quantified the influence of radiometric terrain flattening (RTF) on forest mapping and classification over Austria, and found that it improved the overall accuracy of mapping and classification, with stronger effects in regions with steep topography.
REMOTE SENSING LETTERS
(2022)
Article
Environmental Sciences
Bernhard Bauer-Marschallinger, Senmao Cao, Mark Edwin Tupas, Florian Roth, Claudio Navacchi, Thomas Melzer, Vahid Freeman, Wolfgang Wagner
Summary: By utilizing the systematic monitoring schedule and global land coverage of the Copernicus Sentinel-1 SAR mission, along with a priori generated probability parameters, we developed a datacube-based flood mapping algorithm to enhance the accuracy and robustness of fully automated flood monitoring and classification.
Article
Geography, Physical
Claudio Navacchi, Senmao Cao, Bernhard Bauer-Marschallinger, Paul Snoeij, David Small, Wolfgang Wagner
Summary: This paper discusses the methods of generating backscatter datacubes using the Sentinel-1 mission, introduces a simplified workflow relying on its orbital stability, and proposes some improvements to speed up processing and reduce computational costs.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2022)
Article
Environmental Sciences
Kai Wu, Dongryeol Ryu, Wolfgang Wagner, Zhongmin Hu
Summary: This study aims to advance the use of Triple Collocation Analysis (TCA) for characterizing errors in remotely sensed soil moisture data, particularly focusing on the impact of rescaling techniques and the validation of TCA-based time-variant errors. The findings suggest that different selection of rescaling techniques significantly affects the accuracy of TCA error estimates. The optimal combination strategy is to apply TCA to soil moisture anomalies and rescale errors using coefficients derived from the TCA model. The study highlights the importance of accurate characterization of errors for hydrometeorological applications.
REMOTE SENSING OF ENVIRONMENT
(2023)
Article
Environmental Sciences
Mark Edwin Tupas, Florian Roth, Bernhard Bauer-Marschallinger, Wolfgang Wagner
Summary: With the help of Sentinel-1 mission, the study compared four change detection models and found that the Bayes change detection model performed the best in terms of mapping accuracy due to its scalable classification rules and least sensitivity to parameter choices.
Article
Chemistry, Analytical
Claudio Navacchi, Senmao Cao, Bernhard Bauer-Marschallinger, Paul Snoeij, David Small, Wolfgang Wagner
Summary: Radiometric Terrain Corrected (RTC) gamma nought backscatter has become the standard for analysis-ready SAR data. However, processing large SAR datasets requires substantial computing resources.
Article
Environmental Sciences
Hyunglok Kim, Wade Crow, Xiaojun Li, Wolfgang Wagner, Sebastian Hahn, Venkataraman Lakshmi
Summary: This article discusses the importance of quantifying the accuracy of satellite-based soil moisture data and the limitations of existing statistical methods. It then fills the spatial gaps in TCA results using machine learning and provides spatially complete error maps for satellite-based soil moisture data products. Additionally, SHAP values are used to examine the impact of various environmental conditions on the quality of satellite-based soil moisture retrievals.
REMOTE SENSING OF ENVIRONMENT
(2023)
Article
Environmental Sciences
Isabella Greimeister-Pfeil, Wolfgang Wagner, Raphael Quast, Sebastian Hahn, Susan Steele-Dunne, Mariette Vreugdenhil
Summary: The incidence angle dependence of C-band backscatter is influenced by vegetation and soil moisture, and short-term dynamics might be affected by secondary effects. The study shows that soil moisture has a significant impact on the incidence angle dependence.
SCIENCE OF REMOTE SENSING
(2022)
Article
Geosciences, Multidisciplinary
Paolo Filippucci, Luca Brocca, Raphael Quast, Luca Ciabatta, Carla Saltalippi, Wolfgang Wagner, Angelica Tarpanelli
Summary: The use of satellite sensors to infer rainfall measurements has become a widely used practice in recent years, but their spatial resolution usually exceeds 10 km, which poses an important constraint on its use for applications such as water resource management or hydrological models. In this study, the SM2RAIN algorithm is applied to two soil moisture products over the Po River basin to estimate rainfall. The results show that Sentinel-1 provides reliable rainfall estimates with aggregation time steps greater than 1 day, but ASCAT performs better overall. However, Sentinel-1 outperforms ASCAT in specific areas, highlighting the added value of high-spatial-resolution information.
HYDROLOGY AND EARTH SYSTEM SCIENCES
(2022)
Article
Computer Science, Interdisciplinary Applications
Yapo Abole Serge Innocent Oboue, Yunfeng Chen, Sergey Fomel, Wei Zhong, Yangkang Chen
Summary: Strong noise can disrupt the recorded seismic waves and negatively impact subsequent seismological processes. To improve the signal-to-noise ratio (S/N) of seismological data, we introduce MATamf, an open-source MATLAB code package based on an advanced median filter (AMF) that simultaneously attenuates various types of noise and improves S/N. Experimental results demonstrate the usefulness and advantages of the proposed AMF workflow in enhancing the S/N of a wide range of seismological applications.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Upkar Singh, P. N. Vinayachandran, Vijay Natarajan
Summary: The Bay of Bengal maintains its salinity distribution due to the cyclic flow of high salinity water and the mixing with freshwater. This paper introduces an advection-based feature definition and algorithms to track the movement of high salinity water, validated through comparison with observed data.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Bijal Chudasama, Nikolas Ovaskainen, Jonne Tamminen, Nicklas Nordback, Jon Engstro, Ismo Aaltonen
Summary: This contribution presents a novel U-Net convolutional neural network (CNN)-based workflow for automated mapping of bedrock fracture traces from aerial photographs acquired by unmanned aerial vehicles (UAV). The workflow includes training a U-Net CNN using a small subset of photographs with manually traced fractures, semantic segmentation of input images, pixel-wise identification of fracture traces, ridge detection algorithm and vectorization. The results show the effectiveness and accuracy of the workflow in automated mapping of bedrock fracture traces.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Ruizhen Wang, Siyang Wan, Weitao Chen, Xuwen Qin, Guo Zhang, Lizhe Wang
Summary: This paper proposes a novel framework to generate a finer soil strength map based on RCI, which uses ensemble learning models to obtain USCS soil classification and predict soil moisture, in order to improve the resolution and reliability of existing soil strength maps.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Zhanlong Chen, Xiaochuan Ma, Houpu Li, Xuwei Xu, Xiaoyi Han
Summary: Simulated terrains are important for landform and terrain research, disaster prediction, rescue and disaster relief, and national security. This study proposes a deep learning method, IGPN, that integrates global information and pattern features of the local terrain to generate accurate simulated terrains quickly.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Daniele Secci, Vanessa A. Godoy, J. Jaime Gomez-Hernandez
Summary: Neural networks excel in various machine learning applications, but lack physical interpretability and constraints, limiting their accuracy and reliability in predicting complex physical systems' behavior. Physics-Informed Neural Networks (PINNs) integrate neural networks with physical laws, providing an effective tool for solving physical problems. This article explores recent developments in PINNs, emphasizing their application in solving unconfined groundwater flow, and discusses challenges and opportunities in this field.
COMPUTERS & GEOSCIENCES
(2024)
Article
Computer Science, Interdisciplinary Applications
Renguang Zuo, Ying Xu
Summary: This study proposes a hybrid deep learning model consisting of a one-dimensional convolutional neural network (1DCNN) and a graph convolutional network (GCN) to extract joint spectrum-spatial features from geochemical survey data for mineral exploration. The physically constrained hybrid model performs better in geochemical anomaly recognition compared to other models.
COMPUTERS & GEOSCIENCES
(2024)